DAT-SGD improves the parallelism bound in decentralized stochastic convex optimization from O((ρ√N)^(1/2)) to O(ρ√N), matching centralized rates on dense graphs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Parallelism in Decentralized Stochastic Convex Optimization
DAT-SGD improves the parallelism bound in decentralized stochastic convex optimization from O((ρ√N)^(1/2)) to O(ρ√N), matching centralized rates on dense graphs.